位置:成果数据库 > 期刊 > 期刊详情页
基于边缘差异的印鉴自动鉴别
  • ISSN号:0254-3087
  • 期刊名称:《仪器仪表学报》
  • 时间:0
  • 分类:TP391.4[自动化与计算机技术—计算机应用技术;自动化与计算机技术—计算机科学与技术]
  • 作者机构:[1]天津大学精仪学院光电信息技术科学教育部重点实验室,天津300072
  • 相关基金:国家自然科学基金(No.60627002)资助项目
中文摘要:

提出一种利用待测印鉴(SS)与预留印鉴(MS)之间边缘差异的几何特征判别SS真伪的新方法。利用SIFT(scaleinvariant feature transform)特征配准MS和SS的边缘。刻意伪造的假SS与MS的差异很小,而真印章盖出的不同印鉴也存在微小差异。提出利用不重合的两对应边缘之间的距离和它们的长度判断边缘差异是否由假SS引起。为了便于量化SS与MS边缘的几何差异,定义左差图像LD和右差图像RD。根据Z由和尼,中连通域的位置、长度以及每个连通域中各点的统计特性,计算SS与MS边缘的几何差异大小,将SS判别为真、假或可疑印鉴。对800幅印鉴图像(真、假各400)进行实验。所有假印鉴都被正确识别,6幅真印鉴被识别为可疑印鉴,正确识别率为99.25%

英文摘要:

An automatic seal identification algorithm using geometrical characteristics of edge differences was proposed. Model seal (MS) and sample seal (SS) are registered by matching their SIFT features. The edge difference between MS and a deliberately fake SS is slight, while that between MS and a genuine SS is also small due to the variety of imprinting conditions. To quantify the edge difference, a left difference Lo and a right difference Ro are defined. The connected components in Lo and RD are considered as pieces of non-overlapped edges. The area of each connected component is computed as the length parameter, and the average distance of pixels in each connected component to their corresponding pixels is taken as the distance parameter. According to these two parameters, an SS is classified as true, false or doubtful. 800 sample seals were tested, in which 400 are genuine and 400 are fake. The fake seals are almost identical to their model seals, but none of them was mis-classified. 6 genuine seals that have serious distortions were wrongly regarded as doubtful. The identification precision is 99.25%.

同期刊论文项目
期刊论文 37 会议论文 5 获奖 3 专利 5 著作 3
同项目期刊论文
期刊信息
  • 《仪器仪表学报》
  • 中国科技核心期刊
  • 主管单位:中国科学技术协会
  • 主办单位:中国仪器仪表学会
  • 主编:张钟华
  • 地址:北京东城区北河沿大街79号
  • 邮编:100009
  • 邮箱:yqyb@vip.163.com
  • 电话:010-84050563
  • 国际标准刊号:ISSN:0254-3087
  • 国内统一刊号:ISSN:11-2179/TH
  • 邮发代号:2-369
  • 获奖情况:
  • 1983年评为机械部科技进步三等奖,1997年评为中国科协优秀科技期刊三等奖
  • 国内外数据库收录:
  • 美国化学文摘(网络版),荷兰文摘与引文数据库,美国工程索引,日本日本科学技术振兴机构数据库,中国中国科技核心期刊,中国北大核心期刊(2004版),中国北大核心期刊(2008版),中国北大核心期刊(2011版),中国北大核心期刊(2014版),英国英国皇家化学学会文摘,中国北大核心期刊(2000版)
  • 被引量:42481